Residual Neural Network (ResNet) Based Plant Leaf Disease Detection and Classification

Abstract

Agriculture is the backbone of every country but the more types of Agriculture produces development requirements of today environment. So Ancient agriculture is an unpredictable one and also several problems are included in the traditional Agriculture. This paper introduces a dataset of plant leaf vein images from Rose Leaf, Cucumber Leaf. The Rose Leaf and cucumber leaf is a Dicot because it has a main vein with other veins branching off it. Then multiple instances of the dataset containing 64x64, 32x32, pixel single-channel center-focused images were created, and a new Residual Neural Network (ResNet) based model has applied on each of the instances for group identification. The same procedure is followed for plant leaf disease classification. The aim was to make use of only the vein patterns for the task. The experimental results show that despite the difficulties of recognizing patterns from small-scale images, it is likely to efficiently categorize plant leaf disease by properly deploying residual blocks in neural network models.